Instructions to use limloop/whiff-mamba2-20M with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries

How to use limloop/whiff-mamba2-20M with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="limloop/whiff-mamba2-20M")
messages = [
    {"role": "user", "content": "Who are you?"},
]
pipe(messages)

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("limloop/whiff-mamba2-20M")
model = AutoModelForCausalLM.from_pretrained("limloop/whiff-mamba2-20M", device_map="auto")
messages = [
    {"role": "user", "content": "Who are you?"},
]
inputs = tokenizer.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(tokenizer.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

vLLM

How to use limloop/whiff-mamba2-20M with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "limloop/whiff-mamba2-20M"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "limloop/whiff-mamba2-20M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/limloop/whiff-mamba2-20M

SGLang

How to use limloop/whiff-mamba2-20M with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "limloop/whiff-mamba2-20M" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "limloop/whiff-mamba2-20M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "limloop/whiff-mamba2-20M" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "limloop/whiff-mamba2-20M",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Docker Model Runner
How to use limloop/whiff-mamba2-20M with Docker Model Runner:
```
docker model run hf.co/limloop/whiff-mamba2-20M
```

limloop commited on Oct 20, 2025

Commit

747a9f2

verified ·

1 Parent(s): d41c017

Update README.md

Browse files

Files changed (1) hide show

README.md +7 -7

README.md CHANGED Viewed

@@ -1,7 +1,7 @@
 ---
 license: apache-2.0
 datasets:
-- loim/characters_dialogs
 - IlyaGusev/gpt_roleplay_realm
 - tamohannes/llm-roleplay
 - radce/communication_dataset
@@ -56,8 +56,8 @@ Mamba2Config(
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
-tokenizer = AutoTokenizer.from_pretrained("loim/whiff-mamba2-20M")
-model = AutoModelForCausalLM.from_pretrained("loim/whiff-mamba2-20M")
 def chat(messages, temp=0.5):
     inputs = tokenizer.apply_chat_template(messages, return_tensors="pt")
@@ -96,7 +96,7 @@ print(response)
 Sources:
-- `loim/characters_dialogs`
 - `IlyaGusev/gpt_roleplay_realm`
 - `tamohannes/llm-roleplay`
 - `radce/communication_dataset`
@@ -154,8 +154,8 @@ Mamba2Config(
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
-tokenizer = AutoTokenizer.from_pretrained("loim/whiff-mamba2-20M")
-model = AutoModelForCausalLM.from_pretrained("loim/whiff-mamba2-20M")
 def chat(messages, temp=0.5):
     inputs = tokenizer.apply_chat_template(messages, return_tensors="pt")
@@ -194,7 +194,7 @@ print(response)
 Источники:
-- `loim/characters_dialogs`
 - `IlyaGusev/gpt_roleplay_realm`
 - `tamohannes/llm-roleplay`
 - `radce/communication_dataset`

 ---
 license: apache-2.0
 datasets:
+- limloop/characters_dialogs
 - IlyaGusev/gpt_roleplay_realm
 - tamohannes/llm-roleplay
 - radce/communication_dataset
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("limloop/whiff-mamba2-20M")
+model = AutoModelForCausalLM.from_pretrained("limloop/whiff-mamba2-20M")
 def chat(messages, temp=0.5):
     inputs = tokenizer.apply_chat_template(messages, return_tensors="pt")
 Sources:
+- `limloop/characters_dialogs`
 - `IlyaGusev/gpt_roleplay_realm`
 - `tamohannes/llm-roleplay`
 - `radce/communication_dataset`
 ```python
 from transformers import AutoTokenizer, AutoModelForCausalLM
+tokenizer = AutoTokenizer.from_pretrained("limloop/whiff-mamba2-20M")
+model = AutoModelForCausalLM.from_pretrained("limloop/whiff-mamba2-20M")
 def chat(messages, temp=0.5):
     inputs = tokenizer.apply_chat_template(messages, return_tensors="pt")
 Источники:
+- `limloop/characters_dialogs`
 - `IlyaGusev/gpt_roleplay_realm`
 - `tamohannes/llm-roleplay`
 - `radce/communication_dataset`